Introduce the first user of SLAB bulk free API kmem_cache_free_bulk(),
in the network stack in form of function kfree_skb_bulk() which bulk
free SKBs (not skb clones or skb->head, yet).
As this is the third user of SKB reference decrementing, split out
refcnt decrement into helper function and use this in all call points.
Signed-off-by: Jesper Dangaard Brouer <bro...@redhat.com>
---
include/linux/skbuff.h | 1 +
net/core/skbuff.c | 87 +++++++++++++++++++++++++++++++++++++++---------
2 files changed, 71 insertions(+), 17 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b97597970ce7..e5f1e007723b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -762,6 +762,7 @@ static inline struct rtable *skb_rtable(const struct
sk_buff *skb)
}
void kfree_skb(struct sk_buff *skb);
+void kfree_skb_bulk(struct sk_buff **skbs, unsigned int size);
void kfree_skb_list(struct sk_buff *segs);
void skb_tx_error(struct sk_buff *skb);
void consume_skb(struct sk_buff *skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 429b407b4fe6..034545934158 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -661,26 +661,83 @@ void __kfree_skb(struct sk_buff *skb)
}
EXPORT_SYMBOL(__kfree_skb);
+/*
+ * skb_dec_and_test - Helper to drop ref to SKB and see is ready to free
+ * @skb: buffer to decrement reference
+ *
+ * Drop a reference to the buffer, and return true if it is ready
+ * to free. Which is if the usage count has hit zero or is equal to 1.
+ *
+ * This is performance critical code that should be inlined.
+ */
+static inline bool skb_dec_and_test(struct sk_buff *skb)
+{
+ if (unlikely(!skb))
+ return false;
+ if (likely(atomic_read(&skb->users) == 1))
+ smp_rmb();
+ else if (likely(!atomic_dec_and_test(&skb->users)))
+ return false;
+ /* If reaching here SKB is ready to free */
+ return true;
+}
+
/**
* kfree_skb - free an sk_buff
* @skb: buffer to free
*
* Drop a reference to the buffer and free it if the usage count has
- * hit zero.
+ * hit zero or is equal to 1.
*/
void kfree_skb(struct sk_buff *skb)
{
- if (unlikely(!skb))
- return;
- if (likely(atomic_read(&skb->users) == 1))
- smp_rmb();
- else if (likely(!atomic_dec_and_test(&skb->users)))
- return;
- trace_kfree_skb(skb, __builtin_return_address(0));
- __kfree_skb(skb);
+ if (skb_dec_and_test(skb)) {
+ trace_kfree_skb(skb, __builtin_return_address(0));
+ __kfree_skb(skb);
+ }
}
EXPORT_SYMBOL(kfree_skb);
+/**
+ * kfree_skb_bulk - bulk free SKBs when refcnt allows to
+ * @skbs: array of SKBs to free
+ * @size: number of SKBs in array
+ *
+ * If SKB refcnt allows for free, then release any auxiliary data
+ * and then bulk free SKBs to the SLAB allocator.
+ *
+ * Note that interrupts must be enabled when calling this function.
+ */
+void kfree_skb_bulk(struct sk_buff **skbs, unsigned int size)
+{
+ int i;
+ size_t cnt = 0;
+
+ for (i = 0; i < size; i++) {
+ struct sk_buff *skb = skbs[i];
+
+ if (!skb_dec_and_test(skb))
+ continue; /* skip skb, not ready to free */
+
+ /* Construct an array of SKBs, ready to be free'ed and
+ * cleanup all auxiliary, before bulk free to SLAB.
+ * For now, only handle non-cloned SKBs, related to
+ * SLAB skbuff_head_cache
+ */
+ if (skb->fclone == SKB_FCLONE_UNAVAILABLE) {
+ skb_release_all(skb);
+ skbs[cnt++] = skb;
+ } else {
+ /* SKB was a clone, don't handle this case */
+ __kfree_skb(skb);
+ }
+ }
+ if (likely(cnt)) {
+ kmem_cache_free_bulk(skbuff_head_cache, cnt, (void **) skbs);
+ }
+}
+EXPORT_SYMBOL(kfree_skb_bulk);
+
void kfree_skb_list(struct sk_buff *segs)
{
while (segs) {
@@ -722,14 +779,10 @@ EXPORT_SYMBOL(skb_tx_error);
*/
void consume_skb(struct sk_buff *skb)
{
- if (unlikely(!skb))
- return;
- if (likely(atomic_read(&skb->users) == 1))
- smp_rmb();
- else if (likely(!atomic_dec_and_test(&skb->users)))
- return;
- trace_consume_skb(skb);
- __kfree_skb(skb);
+ if (skb_dec_and_test(skb)) {
+ trace_consume_skb(skb);
+ __kfree_skb(skb);
+ }
}
EXPORT_SYMBOL(consume_skb);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
